INDEX

Explanations

proper nouns, specifically surnames ending in the letter 'w'

oai_token-act-pair · gpt-3.5-turbo

words starting with the letter 'w'

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.10.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

uate

-0.81

 conscientious

-0.72

 paraly

-0.71

âĸ¬

-0.63

uated

-0.58

 vulner

-0.58

 mosqu

-0.57

 suspic

-0.57

 sensitivity

-0.57

 unpre

-0.56

POSITIVE LOGITS

atts

1.37

elcome

1.34

ashington

1.32

itness

1.32

isdom

1.26

izard

1.21

atson

1.19

atcher

1.17

isconsin

1.14

restling

1.13

Activations Density 0.033%

proper nouns, specifically surnames ending in the letter 'w'

words starting with the letter 'w'

No Comments

No Known Activations